Distributed System Performance Degradation Source Identification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

There is a need in distributed systems to determine the source of performance or service degradation that interferes with satisfying required Service Level Agreements (SLA) or Quality of Service (QoS), particularly in networks handling multimedia transmissions where issues like packet dropouts and frame freezing occur.

Innovation Solution

A method and device that model the distributed system, identify associated network components, monitor performance criteria, and determine the source of degradation by analyzing routes and components within the network, using a processor to execute these steps and provide instructions for a computer system to execute the method.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If network bandwidth is increased to guarantee flawless multimedia presentation, then service quality is improved, but network cost and complexity increase

Engineering Contradiction:
Improveservice qualityVSAvoidnetwork complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by proactively monitoring performance criteria and identifying degradation sources before they cause actual service failures. The system continuously tracks network elements and performance metrics, enabling early detection and intervention to prevent packet dropouts and frame freezing, thereby maintaining service quality without requiring excessive network bandwidth

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent implements feedback mechanisms by monitoring performance criteria and using this information to dynamically adjust network routing and resource allocation. The system collects performance data from network elements, analyzes degradation patterns, and adjusts traffic routing in real-time to maintain service quality while optimizing network resource usage

Inventive Principle:
Principle #23Feedback

2Difficulty of detecting and measuring

If network monitoring and analysis capabilities are enhanced to identify performance degradation sources, then troubleshooting efficiency is improved, but system complexity increases

Engineering Contradiction:
Improvedegradation source identificationVSAvoidsystem complexity
Core Design Contradiction:
Difficulty of detecting and measuringVSDevice complexity

Solution Approach 1:

The patent applies segmentation by dividing the network into discrete monitored elements and breaking down performance degradation analysis into specific measurable criteria. The system segments network monitoring into individual element performance tracking and aggregates this data to identify degradation sources, making the complex task of troubleshooting manageable through structured analysis of component-level metrics

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary analysis layer that sits between raw network performance data and troubleshooting decisions. This intermediary system processes performance criteria data, correlates it with network element status, and presents synthesized degradation source identification, simplifying the complexity of analyzing raw network data while improving detection capability

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS8028199B1Method and apparatus for determining a source of performance degradation in distributed systems transmission
Publication Date: 2011.09.27 EMC IP HLDG CO LLC
  • US8028199B1 patent drawing
  • US8028199B1 patent drawing
  • US8028199B1 patent drawing

AI summary

A method, device and computer product suitable for determining the source of failing to achieve a desired level of service quality in communication between at least two components in a distributed system is disclosed. The method comprises the steps of developing a model of the distributed system, the model including at least configuration non-specific representations of types of managed components, and representations of relationships among the managed components, determining associated managed components within each route of data communication between the at least two components, augmenting the representation of the associated managed components with information associated with each of the routes of data communication, monitoring at least one performance criterion of the communication between the at least two components and determining a source of degradation when the performance criteria is indicated to be outside acceptable limits. The device discloses a processor which is capable of executing the method steps recited. The computer program product represents instructions, which when loaded into a computer system provide instruction for the computer system to execute the method steps recited.